Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296c77ace204d16bc303da4af803bd77d3865523c8e73a875386f9f1bf6b012f
+oid sha256:8bb0b59aafdcdad5b80fd82d81c749a7fd8bd10000cc78f8eec192f0b6636b15
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd11974664ae9797c1c038fb65216f2022d8d0b0abd57e05885ecb60d2e34b93
+oid sha256:75ac66074868ff70526cc0fc5f6cf802bb84b1d0cdfef3c62b35a4fcc6e58399
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
+oid sha256:f34cad3af4891ba4d35d6fef0d4d3a99903a2b740801a9646aa2f6b99de9be9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00021248214559748798,
+  "epoch": 0.00023609127288609777,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 17.0,
       "eval_steps_per_second": 17.0,
       "step": 9
+    },
+    {
+      "epoch": 0.00023609127288609777,
+      "grad_norm": 4.921598434448242,
+      "learning_rate": 0.00018,
+      "loss": 2.7927,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 324429435371520.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null